{"uid":"cap_s3MXIe4iurmymR3rFcrNy","slug":"relaystation-vision-detect-labels-a6f97a55","name":"RelayStation Vision Detect Labels","description":"$0.005/image. Detect objects, scenes, and concepts in an image (Rekognition) — labels with confidence scores. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny","url":"https://api.relaystation.ai/v1/vision/detect-labels","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","properties":{"file":{"type":"object","description":"cputools input-source: { inline: <base64 ≤ 4 MiB> } or { inputKey: <scratch key from /v1/cputools/upload-url, ≤ 50 MB> }."},"maxLabels":{"type":"integer","maximum":100,"minimum":1},"minConfidence":{"type":"number","maximum":100,"minimum":0}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ipsA8ki774mbYifAQhsw1","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Detects objects, scenes, and concepts in an image using AWS Rekognition, returning labels with confidence scores","exampleAgentPrompt":"What objects and scenes are in this image? Give me each detected label and its confidence score — the image is at https://example.com/photo.jpg","exampleUseCases":[{"title":"E-commerce product image tagging","prompt":"Can you analyze this product photo at https://mystore.com/items/chair.jpg and tell me all the detected labels and their confidence scores so I can auto-tag it in our catalog?"},{"title":"Content moderation pre-screening","prompt":"I need to know what's in this user-uploaded image at https://cdn.myapp.com/uploads/img123.jpg — list all detected objects and scenes with confidence scores so I can decide if it needs human review."},{"title":"Photo library auto-categorization","prompt":"Run label detection on this photo at https://photos.example.com/vacation/beach01.jpg and tell me every object, scene, and concept Rekognition finds along with confidence percentages."}],"resultDescription":"A list of labels (objects, scenes, concepts) detected in the image, each with a confidence score as a percentage. Labels may include physical objects (e.g. 'Car', 'Tree'), scenes (e.g. 'Beach', 'Office'), and abstract concepts (e.g. 'Adventure', 'Business').","failureModes":["Image URL is inaccessible or returns a non-image response — endpoint cannot fetch the image","Image format is unsupported — returns an error indicating unsupported media type","Image file too large — exceeds Rekognition limits, returns size error","Invalid request payload — missing required image parameter returns 400 bad request","Insufficient x402 payment or credit balance — returns payment required error","Network timeout when fetching remote image URL"],"whenToPreferThis":"Choose this endpoint when you need to identify what is present in an image — objects, scenes, and general concepts — with confidence scores. It is backed by AWS Rekognition, making it highly reliable for general-purpose label detection. Prefer it over face detection endpoints when you need non-face content classification, and over custom ML models when broad category coverage matters more than domain-specific precision. It's well-suited for tagging, content moderation, and catalog enrichment at low cost ($0.005/image).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:55:40.873Z","isFirstParty":false}